Toward Malicious Clients Detection in Federated Learning
Not on the map. Why?
Abstract (arXiv)
Federated learning (FL) enables multiple clients to collaboratively train a global machine learning model without sharing their raw data. However, the decentralized nature of FL introduces vulnerabilities, particularly to poisoning attacks, where malicious clients manipulate their local models to disrupt the training process. While Byzantine-robust aggregation rules have been developed to mitigate such attacks, they remain inadequate against more advanced threats. In response, recent advancements have focused on FL detection techniques to identify potentially malicious participants. Unfortunately, these methods often misclassify numerous benign clients as threats or rely on unrealistic assumptions about the server's capabilities. In this paper, we propose a novel algorithm, SafeFL, specifically designed to accurately identify malicious clients in FL. The SafeFL approach involves the server collecting a series of global models to generate a synthetic dataset, which is then used to distinguish between malicious and benign models based on their behavior. Extensive testing demonstrates that SafeFL outperforms existing methods, offering superior efficiency and accuracy in detecting malicious clients.
Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 46 of its 78 references that are in the map. First posted on arXiv 14 May 2025.
Builds on
46 of 78 references.
References · 46
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2016Deep Learning with Differential Privacycited by 2,728
- 2016Equality of Opportunity in Supervised Learningcited by 2,007
- 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
- 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
- 2019Towards Federated Learning at Scale: System Designcited by 832
- 2018LEAF: A Benchmark for Federated Settingscited by 792
- 2018How To Backdoor Federated Learningcited by 765
- 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
- 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
34 more
- 2020Dataset Condensation with Gradient Matchingcited by 516
- 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
- 2019Agnostic Federated Learningcited by 456
- 2022Dataset Distillation by Matching Training Trajectoriescited by 442
- 2019Fair Resource Allocation in Federated Learningcited by 394
- 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
- 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 346
- 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 288
- 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
- 2022Dataset Condensation via Efficient Synthetic-Data Parameterizationcited by 188
- 2018RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasetscited by 149
- 2020Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcited by 128
- 2022FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clientscited by 125
- 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 118
- 2021Federated Evaluation and Tuning for On-Device Personalization: System Design & Applicationscited by 85
- 2020Defending against Backdoors in Federated Learning with Robust Learning Ratecited by 82
- 2022DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspectioncited by 81
- 2019Byzantine-Robust Federated Machine Learning through Adaptive Model Averagingcited by 70
- 2022MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clientscited by 68
- 2021Decentralized Federated Learning through Proxy Model Sharingcited by 57
- 2020Collaborative Learning in the Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning)cited by 54
- 2024Byzantine-Robust Decentralized Federated Learningcited by 48
- 2019DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregationcited by 44
- 2022AFLGuard: Byzantine-robust Asynchronous Federated Learningcited by 29
- 2023FreqFed: A Frequency Analysis-Based Approach for Mitigating Poisoning Attacks in Federated Learningcited by 27
- 2022DYNAFED: Tackling Client Data Heterogeneity with Global Dynamicscited by 22
- 2024BackdoorIndicator: Leveraging OOD Data for Proactive Backdoor Detection in Federated Learningcited by 17
- 2024Poisoning Federated Recommender Systems with Fake Userscited by 15
- 2025Do We Really Need to Design New Byzantine-robust Aggregation Rules?cited by 15
- 2024Poisoning Attacks on Federated Learning-based Wireless Traffic Predictioncited by 10
- 2025Provably Robust Federated Reinforcement Learningcited by 8
- 2025Byzantine-Robust Federated Learning over Ring-All-Reduce Distributed Computingcited by 6
- 2025Poisoning Attacks and Defenses to Federated Unlearningcited by 5
- 2022Cerberus: Exploring Federated Prediction of Security Eventscited by 4
Built on by
Citing papers per year: 2026: 4.
4 papers.